Back to leaderboard

qwen/qwen3.8-27b

LM-STUDIO MLX

qwen3_5 · 27B · 8bit

Excellent

Aug 18, 2026 · Apple M4 Max

gemma4:26b

OLLAMA GGUF

gemma4 · 25.8B · Q4_K_M

Excellent

Apr 3, 2026 · Apple M4

Global Score
81 vs 85
Hardware Fit
68 vs 77
Quality Score
87 vs 89

Hardware

qwen/qwen3.8-27b gemma4:26b
MachineMacBook ProMac mini
CPUApple M4 MaxApple M4
Cores1610
RAM128 GB24 GB
GPUApple M4 MaxApple M4
OSmacOS 26.5.2macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen/qwen3.8-27b gemma4:26b
Tokens/sec16.424.5
First chunk5 ms1481 ms
TTFT742 ms1.5 s
Load timeN/A24.7 s
Memory usage38.5 GB20.3 GB
Memory %30%85%

HW Fit Score Breakdown

qwen/qwen3.8-27b

Speed
18/50
TTFT
20/20
Memory
30/30

gemma4:26b

Speed
49/50
TTFT
20/20
Memory
8/30

Quality

qwen/qwen3.8-27b

Reasoning
17/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong

gemma4:26b

Reasoning
17/20
Coding
19/20
Instruction
17/20
Structured
14/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

Run yours and compare

$ npm install -g metrillm@latest
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest